Vol.65, No.1, 2020, pp.387-404, doi:10.32604/cmc.2020.010984
A Novel Beam Search to Improve Neural Machine Translation for English-Chinese
  • Xinyue Lin1, Jin Liu1, *, Jianming Zhang2, Se-Jung Lim3
1 College of Information Engineering, Shanghai Maritime University, Shanghai, 201306, China.
2 School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, 410114, China.
3 Liberal Arts & Convergence Studies, Honam University, Gwangju, 62399, Korea.
* Corresponding Author: Jin Liu. Email: jinliu@shmtu.edu.cn.
Received 12 April 2020; Accepted 12 May 2020; Issue published 23 July 2020
Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.
Neural machine translation, beam search, reinforcement learning.
Cite This Article
Lin, X., Liu, J., Zhang, J., Lim, S. (2020). A Novel Beam Search to Improve Neural Machine Translation for English-Chinese. CMC-Computers, Materials & Continua, 65(1), 387–404.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.